asqav
asqav is an AI governance and security platform designed to make AI agents audit-ready by providing real-time monitoring, enforcement, and verifiable proof of every action taken by an agent. It introduces a lightweight SDK that allows developers to integrate governance directly into their agents in just a few lines of code, enabling continuous oversight across the full lifecycle of AI operations. It includes behavioral monitoring to detect issues such as drift, rate limits, and scope violations, along with advanced threat detection that identifies prompt injections, exposure of sensitive data, toxic outputs, and other risks. It enforces policy through configurable “policy gates,” which apply per-agent rules, preflight checks, and dynamic approvals before actions are executed, ensuring that agents operate within defined boundaries. asqav also provides automated incident response capabilities, including the ability to suspend, quarantine, or escalate risky agents.
Learn more
nekuda
Nekuda makes websites actionable for AI agents by adding WebMCP tools that let agents interact with site functions while giving website owners visibility and control over what happens. Teams can build full WebMCP tools with a coding agent or scan a public website and add a single line of code to get initial tools live quickly. Once implemented, it lets businesses create and manage the actions agents can call, such as searching products, retrieving policies, creating checkouts, tracking orders, or updating application data. Nekuda also monitors agent activity, including individual tool calls and complete agent sessions, so teams can understand how agents use their website. Built-in evaluation and testing capabilities measure task success and replay scenarios before and after deployment, helping teams verify that workflows such as search, checkout, policy retrieval, and fallback behavior work as intended.
Learn more
OpenViking
OpenViking is an open source context database designed specifically for AI agents, built around a file-system paradigm that unifies the management of memories, resources, and skills. Instead of treating context as scattered chunks in a fragmented vector store, OpenViking organizes agent context into a virtual file system under the viking protocol, giving agents a structured way to store, navigate, retrieve, and observe the information they need. It is designed to help developers move beyond the hassle of manual context management by giving agents a minimalist interaction model for context, similar to reading and writing files. OpenViking supports hierarchical context loading, semantic retrieval, recursive retrieval, sessions, metrics, and observability, making it possible for AI agents to access the right level of information without stuffing everything into the prompt.
Learn more
FXProof
FXProof is a B2B SaaS for creating signed, verifiable proof documents for official exchange rates. Each reusable proof bundle preserves the selected official source, rate date, dataset details, document ID, payload hash, signature status, and public verification data. It helps accounting and finance teams, bookkeeping and tax practices, auditors, compliance teams, small businesses, freelancers, and software providers document the exchange rate used for invoices, expenses, accounting entries, tax files, internal controls, audits, and dispute reviews. Supported sources include the European Central Bank, HMRC, the Federal Reserve, the Bank of Canada, and the National Bank of Kazakhstan. Users can view proof samples, verify an existing document without an account, retrieve ready proof bundles in the web application, and automate the same workflow through the API. FXProof is not a currency exchange, trading platform, or provider of investment, legal, accounting, or tax advice.
Learn more
